© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189741
    Prev
    Next
    INDEX
    Explanations

    design, therm, attention, shall, idea, conservation, majority

    np_acts-logits-general · gemini-2.5-flash-lite

    expected score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    啼
    0.47
    觛
    0.46
    而成
    0.45
    奂
    0.45
    ింది
    0.44
    пература
    0.44
    是可以
    0.43
    跎
    0.43
    ANDA
    0.43
    预防
    0.42
    POSITIVE LOGITS
     }{
    0.46
    *{
    0.45
     bądź
    0.44
    see
    0.43
    considered
    0.42
    @{
    0.42
     Bajo
    0.42
    returns
    0.41
    filesystem
    0.41
     वर्ल्ड
    0.41
    Activations Density 0.000%

    No Known Activations